Coffee Data Science

Slight Differences in Coffee Roast Development by Taste

Examining Tasting Nuances

Robert McKeon Aloe
4 min readSep 24, 2024

In looking at batch to batch consistency, I wanted to explore how much a minor variation in roast development could affect taste. So I made 4 roasts with 1 second differences in development time. It might have been better to make a few roasts and use color as the distinguishing metric, but that could be a future experiment.

All of these were roasted on the Roest.

Post-Roast Metrics

Three of the four roasts were very close in weight loss and a few other metrics.

Moisture doesn’t have enough resolution to give more definitive answers.

Water activity does show this interesting trend, but I’m not sure if it is statistically meaningful.

Similarly for coffee density, there seems to be a trend for the first three roasts.

For roast color, the last three roasts are very close, and it seems out of place that they should be so different from the first roast.

I also measured ground coffee color, and I observed a similar pattern.

Tasting Equipment/Technique

Espresso Machine: Decent Espresso Machine, Thermal Pre-infusion

Coffee Grinder: Zerno

Coffee: Home Roasted Coffee, medium (First Crack + 1 Minute)

Pre-infusion: Long, ~25 seconds, 30 second ramp bloom, 0.5 ml/s flow during infusion

Filter Basket: 20 Wafo Spirit

Other Equipment: Acaia Pyxis Scale, DiFluid R2 TDS Meter

Metrics of Performance

I used two sets of metrics for evaluating the differences between techniques: Final Score and Coffee Extraction.

Final score is the average of a scorecard of 7 metrics (Sharp, Rich, Syrup, Sweet, Sour, Bitter, and Aftertaste). These scores were subjective, of course, but they were calibrated to my tastes and helped me improve my shots. There is some variation in the scores. My aim was to be consistent for each metric, but some times the granularity was difficult.

Total Dissolved Solids (TDS) is measured using a refractometer, and this number combined with the output weight of the shot and the input weight of the coffee is used to determine the percentage of coffee extracted into the cup, called Extraction Yield (EY).

Data

I pulled four shots per roast, and I pulled a series of shots across all roasts within a day of each other. All these shots were pulled over a period of a few days. The second two roasts were better than the first two. The first two roasts tasted underdeveloped until the last shot.

I reorganized the data by the shot number, so the roast numbers go in order.

All the shots extracted similarly except the last series of shots had a higher EY.

This data is very curious to me as it suggests such minor differences in roast can have such a big impact on the final cup. I’m sure some of the variances were in the green beans themselves, which this experiment did not control for.

If you like, follow me on Twitter, YouTube, and Instagram where I post videos of espresso shots on different machines and espresso related stuff. You can also find me on LinkedIn. You can also follow me on Medium and Subscribe.

Further readings of mine:

My Second Book: Advanced Espresso

My First Book: Engineering Better Espresso

My Links

Collection of Espresso Articles

A Collection of Work and School Stories

--

--

Robert McKeon Aloe

I’m in love with my Wife, my Kids, Espresso, Data Science, tomatoes, cooking, engineering, talking, family, Paris, and Italy, not necessarily in that order.